INDEX

Explanations

negative assessments of ideas or situations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

estyles

-0.48

buttonShape

-0.47

olge

-0.45

<!--[

-0.45

ellees

-0.43

einander

-0.43

ailles

-0.42

lynol

-0.42

[]){

-0.42

 tavola

-0.42

POSITIVE LOGITS

NameInMap

0.84

Diweddarwch

0.84

matchCondition

0.78

ⓧ

0.71

fromnode

0.71

 ComVisible

0.68

WireFormat

0.68

 للاسماء

0.66

imetsu

0.63

:✨

0.63

Activations Density 0.176%

negative assessments of ideas or situations

No Comments

No Known Activations